{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:ARP2IUT5XKUQTIGGGBNSFNN7FT","short_pith_number":"pith:ARP2IUT5","schema_version":"1.0","canonical_sha256":"045fa4527dbaa909a0c6305b22b5bf2cf418116e84dc835c93c7cfffc9b1d931","source":{"kind":"arxiv","id":"1807.04035","version":1},"attestation_state":"computed","paper":{"title":"Modeling Data Lake Metadata with a Data Vault","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Iuri Nogueira (UL2), J\\'er\\^ome Darmont (ERIC), Maram Romdhane (UL2)","submitted_at":"2018-07-11T09:36:34Z","abstract_excerpt":"With the rise of big data, business intelligence had to find solutions for managing even greater data volumes and variety than in data warehouses, which proved ill-adapted. Data lakes answer these needs from a storage point of view, but require managing adequate metadata to guarantee an efficient access to data. Starting from a multidimensional metadata model designed for an industrial heritage data lake presenting a lack of schema evolutivity, we propose in this paper to use ensemble modeling, and more precisely a data vault, to address this issue. To illustrate the feasibility of this approa"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1807.04035","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2018-07-11T09:36:34Z","cross_cats_sorted":[],"title_canon_sha256":"1ac4d165ba4ce3146a2a552325632c85b8bfbd3b6457d9866afc9662d85464e6","abstract_canon_sha256":"06591c0d6a0ac4807209ef57fb71e2b2d6ce31659d1b71d12facec38af83d1d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:10:58.223957Z","signature_b64":"tp7Bcsy48Fpnbc1ERlKV/GL3C6RnbcgrF4KvB+chmeHgMl3uT5KmPx9Tbk1Ij3gN0mqIhc0mrMBEme+W2EwXAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"045fa4527dbaa909a0c6305b22b5bf2cf418116e84dc835c93c7cfffc9b1d931","last_reissued_at":"2026-05-18T00:10:58.223293Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:10:58.223293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Modeling Data Lake Metadata with a Data Vault","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Iuri Nogueira (UL2), J\\'er\\^ome Darmont (ERIC), Maram Romdhane (UL2)","submitted_at":"2018-07-11T09:36:34Z","abstract_excerpt":"With the rise of big data, business intelligence had to find solutions for managing even greater data volumes and variety than in data warehouses, which proved ill-adapted. Data lakes answer these needs from a storage point of view, but require managing adequate metadata to guarantee an efficient access to data. Starting from a multidimensional metadata model designed for an industrial heritage data lake presenting a lack of schema evolutivity, we propose in this paper to use ensemble modeling, and more precisely a data vault, to address this issue. To illustrate the feasibility of this approa"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.04035","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"1807.04035","created_at":"2026-05-18T00:10:58.223409+00:00"},{"alias_kind":"arxiv_version","alias_value":"1807.04035v1","created_at":"2026-05-18T00:10:58.223409+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.04035","created_at":"2026-05-18T00:10:58.223409+00:00"},{"alias_kind":"pith_short_12","alias_value":"ARP2IUT5XKUQ","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_16","alias_value":"ARP2IUT5XKUQTIGG","created_at":"2026-05-18T12:32:13.499390+00:00"},{"alias_kind":"pith_short_8","alias_value":"ARP2IUT5","created_at":"2026-05-18T12:32:13.499390+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ARP2IUT5XKUQTIGGGBNSFNN7FT","json":"https://pith.science/pith/ARP2IUT5XKUQTIGGGBNSFNN7FT.json","graph_json":"https://pith.science/api/pith-number/ARP2IUT5XKUQTIGGGBNSFNN7FT/graph.json","events_json":"https://pith.science/api/pith-number/ARP2IUT5XKUQTIGGGBNSFNN7FT/events.json","paper":"https://pith.science/paper/ARP2IUT5"},"agent_actions":{"view_html":"https://pith.science/pith/ARP2IUT5XKUQTIGGGBNSFNN7FT","download_json":"https://pith.science/pith/ARP2IUT5XKUQTIGGGBNSFNN7FT.json","view_paper":"https://pith.science/paper/ARP2IUT5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1807.04035&json=true","fetch_graph":"https://pith.science/api/pith-number/ARP2IUT5XKUQTIGGGBNSFNN7FT/graph.json","fetch_events":"https://pith.science/api/pith-number/ARP2IUT5XKUQTIGGGBNSFNN7FT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ARP2IUT5XKUQTIGGGBNSFNN7FT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ARP2IUT5XKUQTIGGGBNSFNN7FT/action/storage_attestation","attest_author":"https://pith.science/pith/ARP2IUT5XKUQTIGGGBNSFNN7FT/action/author_attestation","sign_citation":"https://pith.science/pith/ARP2IUT5XKUQTIGGGBNSFNN7FT/action/citation_signature","submit_replication":"https://pith.science/pith/ARP2IUT5XKUQTIGGGBNSFNN7FT/action/replication_record"}},"created_at":"2026-05-18T00:10:58.223409+00:00","updated_at":"2026-05-18T00:10:58.223409+00:00"}